CanXP training job 477fb32c

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

LICENSE_NOTICE.txt

@@ -0,0 +1,19 @@
+Model License Notice
+====================
+
+This fine-tuned model is derived from the base model:
+
+    empero-ai/Qwythos-9B-Claude-Mythos-5-1M     (MaplePT-Reasoning base — Qwythos 9B (Frontier Reasoning))
+
+The base model is distributed under the following license:
+
+    Apache-2.0
+    https://www.apache.org/licenses/LICENSE-2.0
+
+Your fine-tuned weights and adapters inherit the obligations of this license.
+By distributing or deploying this model you agree to comply with the upstream
+license terms (including any attribution, redistribution, gating, or
+acceptable-use policies).
+
+Customer-provided training data is not included in this artifact bundle. The
+trained weights/adapters may, however, encode information from that data.

README.md

@@ -0,0 +1,57 @@
+---
+license: other
+base_model: empero-ai/Qwythos-9B-Claude-Mythos-5-1M
+tags:
+  - canxp
+  - lora
+  - peft
+  - lora
+---
+
+# maplept2-reasoning
+
+Fine-tuned by **CanXP AI** ([canxp.ai](https://canxp.ai)) from base model
+`empero-ai/Qwythos-9B-Claude-Mythos-5-1M` using LORA.
+
+## Quick start (Python)
+
+```bash
+pip install transformers peft torch
+```
+
+```python
+from transformers import AutoTokenizer, AutoModelForCausalLM
+from peft import PeftModel
+
+base = "empero-ai/Qwythos-9B-Claude-Mythos-5-1M"
+adapter = "canxp-ai/maplept2-reasoning-477fb32c"
+
+tokenizer = AutoTokenizer.from_pretrained(base, trust_remote_code=True)
+model = AutoModelForCausalLM.from_pretrained(
+    base, torch_dtype="bfloat16", device_map="auto", trust_remote_code=True
+)
+model = PeftModel.from_pretrained(model, adapter)
+
+prompt = "Hello!"
+inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
+out = model.generate(**inputs, max_new_tokens=200)
+print(tokenizer.decode(out[0], skip_special_tokens=True))
+```
+
+## CLI download
+
+```bash
+pip install -U "huggingface_hub[cli]"
+huggingface-cli download canxp-ai/maplept2-reasoning-477fb32c --local-dir ./maplept2-reasoning
+```
+
+## Training details
+
+- Base model: `empero-ai/Qwythos-9B-Claude-Mythos-5-1M`
+- Method: LORA
+- Epochs: 3
+- Context length: 4096
+- Validation split: 0.05
+
+This adapter inherits the upstream license of the base model. See
+LICENSE_NOTICE.txt in this repo for details.

adapter_config.json

@@ -0,0 +1,53 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "empero-ai/Qwythos-9B-Claude-Mythos-5-1M",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 512,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.19.1",
+  "qalora_group_size": 16,
+  "r": 256,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "in_proj_a",
+    "in_proj_qkv",
+    "o_proj",
+    "k_proj",
+    "in_proj_b",
+    "v_proj",
+    "q_proj",
+    "gate_proj",
+    "out_proj",
+    "in_proj_z",
+    "down_proj",
+    "up_proj"
+  ],
+  "target_parameters": [],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0479178d1cbd60cd2a3ef943a9f50d8a090f522a92c6719f224042036f2bde88
+size 2769890408

chat_template.jinja

@@ -0,0 +1,4 @@
+{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '
+' + message['content'] + '<|im_end|>' + '
+'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant
+' }}{% endif %}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:639e352c0f904c1875d448ebed6f6faac005fd3eb58393b7f1fb3ff044e5ca03
+size 19989510

tokenizer_config.json

@@ -0,0 +1,37 @@
+{
+  "add_prefix_space": false,
+  "audio_bos_token": "<|audio_start|>",
+  "audio_eos_token": "<|audio_end|>",
+  "audio_token": "<|audio_pad|>",
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "image_token": "<|image_pad|>",
+  "is_local": false,
+  "local_files_only": false,
+  "max_length": null,
+  "model_max_length": 262144,
+  "model_specific_special_tokens": {
+    "audio_bos_token": "<|audio_start|>",
+    "audio_eos_token": "<|audio_end|>",
+    "audio_token": "<|audio_pad|>",
+    "image_token": "<|image_pad|>",
+    "video_token": "<|video_pad|>",
+    "vision_bos_token": "<|vision_start|>",
+    "vision_eos_token": "<|vision_end|>"
+  },
+  "pad_to_multiple_of": null,
+  "pad_token": "<|endoftext|>",
+  "pad_token_type_id": 0,
+  "padding_side": "left",
+  "pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
+  "processor_class": "Qwen3VLProcessor",
+  "split_special_tokens": false,
+  "tokenizer_class": "TokenizersBackend",
+  "unk_token": null,
+  "video_token": "<|video_pad|>",
+  "vision_bos_token": "<|vision_start|>",
+  "vision_eos_token": "<|vision_end|>"
+}